# Hierarchically Decoupled Imitation for Morphological Transfer

arXiv: https://arxiv.org/abs/2003.01709 · HTML: https://mlsanity.com/paper/2003.01709/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2020.

## Built on by (most cited first, 30 of 31)

- [XIRL: Cross-embodiment Inverse Reinforcement Learning](https://mlsanity.com/paper/2106.03911/) (2021)
- [Cross-Domain Imitation Learning via Optimal Transport](https://mlsanity.com/paper/2110.03684/) (2021)
- [Cross-Domain Policy Adaptation via Value-Guided Data Filtering](https://mlsanity.com/paper/2305.17625/) (2023)
- [AnyMorph: Learning Transferable Polices By Inferring Agent Morphology](https://mlsanity.com/paper/2206.12279/) (2022)
- [Cross-Embodiment Dexterous Grasping with Reinforcement Learning](https://mlsanity.com/paper/2410.02479/) (2024)
- [Cross-Domain Policy Adaptation by Capturing Representation Mismatch](https://mlsanity.com/paper/2405.15369/) (2024)
- [ODRL: A Benchmark for Off-Dynamics Reinforcement Learning](https://mlsanity.com/paper/2410.20750/) (2024)
- [Cross-Embodiment Robot Manipulation Skill Transfer using Latent Space Alignment](https://mlsanity.com/paper/2406.01968/) (2024)
- [AdaptNet: Policy Adaptation for Physics-Based Character Control](https://mlsanity.com/paper/2310.00239/) (2023)
- [A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents](https://mlsanity.com/paper/2402.04580/) (2024)
- [REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer](https://mlsanity.com/paper/2202.05244/) (2022)
- [A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation](https://mlsanity.com/paper/2211.14296/) (2022)
- [xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing](https://mlsanity.com/paper/2409.08687/) (2024)
- [Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data](https://mlsanity.com/paper/2505.23062/) (2025)
- [Cross Domain Robot Imitation with Invariant Representation](https://mlsanity.com/paper/2109.05940/) (2021)
- [Cross Domain Policy Transfer with Effect Cycle-Consistency](https://mlsanity.com/paper/2403.02018/) (2024)
- [Hierarchically Integrated Models: Learning to Navigate from Heterogeneous Robots](https://mlsanity.com/paper/2106.13280/) (2021)
- [Offline Reinforcement Learning with Domain-Unlabeled Data](https://mlsanity.com/paper/2404.07465/) (2024)
- [Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer](https://mlsanity.com/paper/2405.03534/) (2024)
- [Teachable Reinforcement Learning via Advice Distillation](https://mlsanity.com/paper/2203.11197/) (2022)
- [Correspondence learning between morphologically different robots via task demonstrations](https://mlsanity.com/paper/2310.13458/) (2023)
- [Knowledge Transfer for Cross-Domain Reinforcement Learning: A Systematic Review](https://mlsanity.com/paper/2404.17687/) (2024)
- [A Minimalist Prompt for Zero-Shot Policy Learning](https://mlsanity.com/paper/2405.06063/) (2024)
- [Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning](https://mlsanity.com/paper/2506.12529/) (2025)
- [A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalization](https://mlsanity.com/paper/2202.08444/) (2022)
- [MeMo: Meaningful, Modular Controllers via Noise Injection](https://mlsanity.com/paper/2407.01567/) (2024)
- [Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral Cloning](https://mlsanity.com/paper/2407.16912/) (2024)
- [Cross-Domain Offline Policy Adaptation via Selective Transition Correction](https://mlsanity.com/paper/2602.05776/) (2026)
- [SHIRO: Soft Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2212.12786/) (2022)
- [MorFiC: Fixing Value Miscalibration for Zero-Shot Quadruped Transfer](https://mlsanity.com/paper/2603.14554/) (2026)

## Abstract (arXiv)

Learning long-range behaviors on complex high-dimensional agents is a fundamental problem in robot learning. For such tasks, we argue that transferring learned information from a morphologically simpler agent can massively improve the sample efficiency of a more complex one. To this end, we propose a hierarchical decoupling of policies into two parts: an independently learned low-level policy and a transferable high-level policy. To remedy poor transfer performance due to mismatch in morphologies, we contribute two key ideas. First, we show that incentivizing a complex agent's low-level to imitate a simpler agent's low-level significantly improves zero-shot high-level transfer. Second, we show that KL-regularized training of the high level stabilizes learning and prevents mode-collapse. Finally, on a suite of publicly released navigation and manipulation environments, we demonstrate the applicability of hierarchical transfer on long-range tasks across morphologies. Our code and videos can be found at https://sites.google.com/berkeley.edu/morphology-transfer.